PulseAugur
LIVE 10:54:46
research · [2 sources] ·
0
research

RAG+prompt system boosts Japanese-Chinese translation accuracy with linguistic analysis

Researchers have developed a retrieval-augmented generation (RAG) system combined with prompting techniques to improve Japanese-Chinese machine translation, particularly for sentences with noun-modifying clause constructions (NMCCs). The system integrates linguistic analysis, embedding-based retrieval, and prompt engineering to enhance the output of large language models like GPT-4o. Testing with various knowledge base sizes showed a significant increase in BLEU scores, with larger bases yielding better results, demonstrating an interpretable and auditable method for translation improvement. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT This RAG+prompt system offers a more interpretable and auditable approach to improving LLM translation quality for complex linguistic structures.

RANK_REASON The cluster contains an academic paper detailing a new RAG+prompt system for machine translation.

Read on arXiv cs.CL →

COVERAGE [2]

  1. arXiv cs.CL TIER_1 · Wenshi Gu ·

    From prompting to evidence-based translation: A RAG+prompt system for Japanese-Chinese translation and its pedagogical potential

    arXiv:2605.03387v1 Announce Type: new Abstract: Large language models perform well on high-resource pairs but are less reliable for Japanese-Chinese sentences containing noun-modifying clause constructions (NMCCs). This study evaluates a retrieval-augmented generation RAG+Prompt …

  2. arXiv cs.CL TIER_1 · Wenshi Gu ·

    From prompting to evidence-based translation: A RAG+prompt system for Japanese-Chinese translation and its pedagogical potential

    Large language models perform well on high-resource pairs but are less reliable for Japanese-Chinese sentences containing noun-modifying clause constructions (NMCCs). This study evaluates a retrieval-augmented generation RAG+Prompt translation system that integrates linguistic an…